ImageNet Large Scale Visual Recognition Challenge (ILSVRC) is one of the most authoritative academic competitions in the field of Computer Vision (CV) in recent years, but it can not achieve good result to directly migrate the champions of the annual competition, to fine-grained visual categorization (FGVC) tasks. The small interclass variations and the large intraclass variations caused by the fine-grained nature makes it a challenging problem. The proposed method can be effectively localize object and useful part regions without the need of bounding-box and part annotations by attention object location module (AOLM) and attention part proposal module (APPM). The obtained object images contain both the whole structure and more details, the part images have many different scales and have more fine-grained features, and the raw images contain the complete object. The three kinds of training images are supervised by our three-branch network structure. The model has good classification ability, good generalization and robustness for different scale object images. Our approach is end-to-end training, through the comprehensive experiments demonstrate that our approach achieves state-of-the-art results on CUB-200-2011, Stanford Cars and FGVC-Aircraft datasets.
Layer-wise learning, as an alternative to global back-propagation, is easy to interpret, analyze, and it is memory efficient. Recent studies demonstrate that layer-wise learning can achieve state-of-the-art performance in image classification on various datasets. However, previous studies of layer-wise learning are limited to networks with simple hierarchical structures, and the performance decreases severely for deeper networks like ResNet. This paper, for the first time, reveals the fundamental reason that impedes the scale-up of layer-wise learning is due to the relatively poor separability of the feature space in shallow layers. This argument is empirically verified by controlling the intensity of the convolution operation in local layers. We discover that the poorly-separable features from shallow layers are mismatched with the strong supervision constraint throughout the entire network, making the layer-wise learning sensitive to network depth. The paper further proposes a downsampling acceleration approach to weaken the poor learning of shallow layers so as to transfer the learning emphasis to deep feature space where the separability matches better with the supervision restraint. Extensive experiments have been conducted to verify the new finding and demonstrate the advantages of the proposed downsampling acceleration in improving the performance of layer-wise learning.
Learning a suitable graph is an important precursor to many graph signal processing (GSP) pipelines, such as graph spectral signal compression and denoising. Previous graph learning algorithms either i) make some assumptions on connectivity (e.g., graph sparsity), or ii) make simple graph edge assumptions such as positive edges only. In this paper, given an empirical covariance matrix $\bar{C}$ computed from data as input, we consider a structural assumption on the graph Laplacian matrix $L$: the first $K$ eigenvectors of $L$ are pre-selected, e.g., based on domain-specific criteria, such as computation requirement, and the remaining eigenvectors are then learned from data. One example use case is image coding, where the first eigenvector is pre-chosen to be constant, regardless of available observed data. We first prove that the subspace of symmetric positive semi-definite (PSD) matrices $H_{u}^+$ with the first $K$ eigenvectors being $\{u_k\}$ in a defined Hilbert space is a convex cone. We then construct an operator to project a given positive definite (PD) matrix $L$ to $H_{u}^+$, inspired by the Gram-Schmidt procedure. Finally, we design an efficient hybrid graphical lasso/projection algorithm to compute the most suitable graph Laplacian matrix $L^* \in H_{u}^+$ given $\bar{C}$. Experimental results show that given the first $K$ eigenvectors as a prior, our algorithm outperforms competing graph learning schemes using a variety of graph comparison metrics.
Arterial spin labeling (ASL) perfusion MRI provides a non-invasive way to quantify cerebral blood flow (CBF) but it still suffers from a low signal-to-noise-ratio (SNR). Using deep machine learning (DL), several groups have shown encouraging denoising results. Interestingly, the improvement was obtained when the deep neural network was trained using noise-contaminated surrogate reference because of the lack of golden standard high quality ASL CBF images. More strikingly, the output of these DL ASL networks (ASLDN) showed even higher SNR than the surrogate reference. This phenomenon indicates a learning-from-noise capability of deep networks for ASL CBF image denoising, which can be further enhanced by network optimization. In this study, we proposed a new ASLDN to test whether similar or even better ASL CBF image quality can be achieved in the case of highly noisy training reference. Different experiments were performed to validate the learning-from-noise hypothesis. The results showed that the learning-from-noise strategy produced better output quality than ASLDN trained with relatively high SNR reference.
Due to the compelling efficiency in retrieval and storage, similarity-preserving hashing has been widely applied to approximate nearest neighbor search in large-scale image retrieval. However, existing methods have poor performance in retrieval using an extremely short-length hash code due to weak ability of classification and poor distribution of hash bit. To address this issue, in this study, we propose a novel reinforcing short-length hashing (RSLH). In this proposed RSLH, mutual reconstruction between the hash representation and semantic labels is performed to preserve the semantic information. Furthermore, to enhance the accuracy of hash representation, a pairwise similarity matrix is designed to make a balance between accuracy and training expenditure on memory. In addition, a parameter boosting strategy is integrated to reinforce the precision with hash bits fusion. Extensive experiments on three large-scale image benchmarks demonstrate the superior performance of RSLH under various short-length hashing scenarios.
We present a generalized and scalable method, called Gen-LaneNet, to detect 3D lanes from a single image. The method, inspired by the latest state-of-the-art 3D-LaneNet, is a unified framework solving image encoding, spatial transform of features and 3D lane prediction in a single network. However, we propose unique designs for Gen-LaneNet in two folds. First, we introduce a new geometry-guided lane anchor representation in a new coordinate frame and apply a specific geometric transformation to directly calculate real 3D lane points from the network output. We demonstrate that aligning the lane points with the underlying top-view features in the new coordinate frame is critical towards a generalized method in handling unfamiliar scenes. Second, we present a scalable two-stage framework that decouples the learning of image segmentation subnetwork and geometry encoding subnetwork. Compared to 3D-LaneNet, the proposed Gen-LaneNet drastically reduces the amount of 3D lane labels required to achieve a robust solution in real-world application. Moreover, we release a new synthetic dataset and its construction strategy to encourage the development and evaluation of 3D lane detection methods. In experiments, we conduct extensive ablation study to substantiate the proposed Gen-LaneNet significantly outperforms 3D-LaneNet in average precision(AP) and F-score.
State-of-the-art computer vision models are rapidly increasing in capacity, where the number of parameters far exceeds the number required to fit the training set. This results in better optimization and generalization performance. However, the huge size of contemporary models results in large inference costs and limits their use on resource-limited devices. In order to reduce inference costs, convolutional filters in trained neural networks could be pruned to reduce the run-time memory and computational requirements during inference. However, severe post-training pruning results in degraded performance if the training algorithm results in dense weight vectors. We propose the use of Batch Bridgeout, a sparsity inducing stochastic regularization scheme, to train neural networks so that they could be pruned efficiently with minimal degradation in performance. We evaluate the proposed method on common computer vision models VGGNet, ResNet, and Wide-ResNet on the CIFAR image classification task. For all the networks, experimental results show that Batch Bridgeout trained networks achieve higher accuracy across a wide range of pruning intensities compared to Dropout and weight decay regularization.
Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. Here we explore the applicability of transfer learning utilizing models pre-trained on non-software engineering data applied to the problem of classifying software UML diagrams. Our experimental results show training reacts positively to transfer learning as related to sample size, even though the pre-trained model was not exposed to training instances from the software domain. We contrast the transferred network with other networks to show its advantage on different sized training sets, which indicates that transfer learning is equally effective to custom deep architectures when large amounts of training data is not available.
Despite tremendous success in many application scenarios, deep learning faces serious intellectual property (IP) infringement threats. Considering the cost of designing and training a good model, infringements will significantly infringe the interests of the original model owner. Recently, many impressive works have emerged for deep model IP protection. However, they either are vulnerable to ambiguity attacks, or require changes in the target network structure by replacing its original normalization layers and hence cause significant performance drops. To this end, we propose a new passport-aware normalization formulation, which is generally applicable to most existing normalization layers and only needs to add another passport-aware branch for IP protection. This new branch is jointly trained with the target model but discarded in the inference stage. Therefore it causes no structure change in the target model. Only when the model IP is suspected to be stolen by someone, the private passport-aware branch is added back for ownership verification. Through extensive experiments, we verify its effectiveness in both image and 3D point recognition models. It is demonstrated to be robust not only to common attack techniques like fine-tuning and model compression, but also to ambiguity attacks. By further combining it with trigger-set based methods, both black-box and white-box verification can be achieved for enhanced security of deep learning models deployed in real systems. Code can be found at https://github.com/ZJZAC/Passport-aware-Normalization.
Basic group of visual techniques such as color, shape, texture are used in Content Based Image Retrievals (CBIR) to retrieve query image or subregion of image to find similar images in image database. To improve query result, relevance feedback is used many times in CBIR to help user to express their preference and improve query results.In this paper, a new approach for image retrieval is proposed which is based on the features such as Color Histogram, Eigen Values and Match Point. Images from various types of database are first identified by using edge detection techniques.Once the image is identified, then the image is searched in the particular database, then all related images are displayed. This will save the retrieval time. Further to retrieve the precise query image, any of the three techniques are used and comparison is done w.r.t. average retrieval time. Eigen value technique found to be the best as compared with other two techniques